Inspired by progress in large-scale language modeling, we apply a similar approach towards
building a single generalist agent beyond the realm of text outputs. The agent, which we …

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy
optimization from large pre-recorded datasets without online environment interaction. It …

Offline reinforcement learning (RL purely from logged data) is an important avenue for
deploying RL techniques in real-world scenarios. However, existing hyperparameter selection …

Offline methods for reinforcement learning have a potential to help bridge the gap between
reinforcement learning research and real-world applications. They make it possible to learn …

The ability to leverage heterogeneous robotic experience from different robots and tasks to
quickly master novel skills and embodiments has the potential to transform robot learning. …

Behavior cloning (BC) is often practical for robot learning because it allows a policy to be
trained offline without rewards, by supervised learning on expert demonstrations. However, BC …

We present a framework for data-driven robotics that makes use of a large dataset of recorded
robot experience and scales to several tasks using learned reward functions. We show …

We introduce Genie, the first *generative interactive environment* trained in an unsupervised
manner from unlabelled Internet videos. The model can be prompted to generate an …

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator
networks to learn spurious associations between visual features and expert labels. When the …

Recurrent neural networks (RNNs) are important class of architectures among neural networks
useful for language modeling and sequential prediction. However, optimizing RNNs is …